Repositories list

• CPM.cu

  Public
  CPM.cu is a lightweight, high-performance CUDA implementation for LLMs, optimized for end-device inference and featuring cutting-edge techniques in sparse architecture, speculative sampling and quantization.

  Cuda

  •

  Apache License 2.0

  •14•166•3•1•Updated Aug 1, 2025Aug 1, 2025

• MiniCPM-o

  Public
  MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

  multi-modalminicpmminicpm-v

  Python

  •

  Apache License 2.0

  •1.5k•20k•57•15•Updated Jul 31, 2025Jul 31, 2025

• RLPR

  Public
  Extrapolating RLVR to General Domains without Verifiers

  Python

  •

  Apache License 2.0

  •8•134•0•0•Updated Jul 29, 2025Jul 29, 2025

• UltraEval-Audio

  Public
  An easy-to-use, fast, and easily integrable tool for evaluating audio LLM

  evaluationspeech-recognitionspeech-to-text+ 1speech-to-speech

  Python

  •

  Apache License 2.0

  •4•128•11•0•Updated Jul 28, 2025Jul 28, 2025

• ChatDev

  Public
  Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

  Python

  •

  Apache License 2.0

  •3.4k•27k•22•24•Updated Jul 22, 2025Jul 22, 2025

• MiniCPM

  Public
  MiniCPM4: Ultra-Efficient LLMs on End Devices, achieving 5+ speedup on typical end-side chips

  Jupyter Notebook

  •

  Apache License 2.0

  •505•8.1k•14•0•Updated Jul 8, 2025Jul 8, 2025

• MiniCPM-CookBook

  Public
  This is a user guide for the MiniCPM and MiniCPM-V series of small language models (SLMs) developed by ModelBest. “面壁小钢炮” focuses on achieving exceptional performance on the edge.

  Python

  •24•264•0•2•Updated Jul 1, 2025Jul 1, 2025

• ParamMute

  Public
  ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation

  Python

  •1•38•1•0•Updated Jun 20, 2025Jun 20, 2025

• AgentCPM-GUI

  Public
  AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution.

  Python

  •

  Apache License 2.0

  •95•954•18•0•Updated Jun 14, 2025Jun 14, 2025

• OlympiadBench

  Public
  [ACL 2024]Official GitHub repo for OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

  Python

  •

  MIT License

  •9•164•5•0•Updated Jun 8, 2025Jun 8, 2025

• sglang

  Public
  SGLang is a fast serving framework for large language models and vision language models.

  Python

  •

  Apache License 2.0

  •2.5k•2•0•0•Updated Jun 6, 2025Jun 6, 2025

• infllmv2_cuda_impl

  Public
  C++

  •3•39•0•0•Updated Jun 6, 2025Jun 6, 2025

• OpenAct

  Public
  HTML

  •0•3•1•0•Updated May 31, 2025May 31, 2025

• BMTrain

  Public
  Efficient Training (including pre-training and fine-tuning) for Big Models

  Python

  •

  Apache License 2.0

  •81•604•5•5•Updated May 29, 2025May 29, 2025

• R1-Router

  Public
  This is the code repo for the paper "Learning to Route Queries Across Knowledge Bases for Step-wise Retrieval-Augmented Reasoning".

  Python

  •0•22•0•0•Updated May 29, 2025May 29, 2025

• ToolBench

  Public
  [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

  Python

  •

  Apache License 2.0

  •446•5.2k•132•7•Updated May 21, 2025May 21, 2025

• UltraRAG

  Public
  Build & Optimize your RAG.

  easywebuigpt+ 7embeddingfinetuneragllmllamaindexminicpmbge-m3

  Python

  •

  Apache License 2.0

  •56•728•0•0•Updated May 13, 2025May 13, 2025

• RAGEval

  Public
  Python

  •

  Other

  •13•183•4•1•Updated Apr 2, 2025Apr 2, 2025

• ConsJudge

  Public
  Python

  •

  MIT License

  •0•11•0•0•Updated Mar 23, 2025Mar 23, 2025

• WorkflowLLM

  Public
  An open platform for enhancing the capability of LLMs in workflow orchestration.

  Python

  •

  Apache License 2.0

  •20•159•3•0•Updated Mar 11, 2025Mar 11, 2025

• DEBATER

  Public
  This is the code repo for our paper "Learning More Effective Representations for Dense Retrieval through Deliberate Thinking Before Search".

  Python

  •2•23•1•1•Updated Mar 2, 2025Mar 2, 2025

• VisRAG

  Public
  Parsing-free RAG supported by VLMs

  retrievalmulti-modaldocument-retrieval+ 5ragmulti-modalitydocument-understandingvision-language-modelretrieval-augmented-generation

  Python

  •

  Apache License 2.0

  •59•762•1•0•Updated Feb 19, 2025Feb 19, 2025

• UltraLink

  Public
  An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset

  Python

  •

  MIT License

  •3•25•0•0•Updated Jan 19, 2025Jan 19, 2025

• RepoAgent

  Public
  An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

  agentllamagpt+ 10raggpt-4llmschatgptlangchainchatgpt-apillama-index+ 3

  Python

  •

  Apache License 2.0

  •107•741•10•1•Updated Dec 23, 2024Dec 23, 2024

• DecorateLM

  Public
  Python

  •

  MIT License

  •2•8•0•0•Updated Dec 17, 2024Dec 17, 2024

• RaD-Agent

  Public
  The official implementation of the Rational Decision-Making Agent with Internalized Utility Judgment

  Python

  •1•5•0•0•Updated Nov 12, 2024Nov 12, 2024

• UltraEval

  Public
  [ACL 2024 Demo] Official GitHub repo for UltraEval: An open source framework for evaluating foundation models.

  Python

  •

  Apache License 2.0

  •22•245•4•0•Updated Oct 30, 2024Oct 30, 2024

• Locret

  Public
  Python

  •1•2•0•0•Updated Oct 29, 2024Oct 29, 2024

• RAG-DDR

  Public
  This is the code repo for the paper "RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards".

  Python

  •

  MIT License

  •2•21•0•0•Updated Oct 28, 2024Oct 28, 2024

• IoA

  Public
  An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.

  agentaiioa+ 2llmgenai

  Python

  •

  Apache License 2.0

  •76•745•10•1•Updated Oct 20, 2024Oct 20, 2024